I Have Adhd
Reshapes replies for ADHD readers: action first, numbered steps, no preamble or closers
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 98e9a44
Located SKILL.md at skills/i-have-adhd/SKILL.md (also mirrored at .cursor/skills/); frontmatter parses with name+description and all spot-checked files return HTTP 200 (SKILL.md, hooks/always-on.sh, agents/openai.yaml). Read hooks/always-on.sh: clean POSIX sh, opt-in via a flag file, strips frontmatter and injects the body, exits 0 on failure — no curl|sh, base64, exfiltration, or hardcoded paths. For the output test I answered one coding question ("add a rate limiter to Express") twice: a baseline in my default voice (opened "Great question!", buried steps in prose, closed "Hope this helps") and a skill-following version (first line = runnable command, 3 numbered steps, "About 5 minutes" estimate, testable next action, Redis caveat deferred as a separate offer). The two artifacts differ concretely on 6 axes matching Rules 1,2,4,6,7,10. Note: disable-model-invocation:true means it only fires via /i-have-adhd or the always-on hook, which the description discloses honestly.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What I Have Adhd does
A Claude Code output-style skill that reshapes assistant responses for an ADHD reader: it leads with the next runnable action, numbers multi-step work, restates progress each turn, suppresses tangents, gives concrete time estimates, and strips preamble and closers. Triggers only on explicit /i-have-adhd invocation (model auto-invocation is disabled) or via an opt-in SessionStart hook.
How to install I Have Adhd
git clone --depth 1 https://github.com/ayghri/i-have-adhd.git /tmp/i-have-adhd-src
mkdir -p ~/.claude/skills
cp -R /tmp/i-have-adhd-src/skills/i-have-adhd ~/.claude/skills/i-have-adhd
# SKILL.md lands at ~/.claude/skills/i-have-adhd/SKILL.md
# Invoke explicitly with /i-have-adhd (frontmatter sets disable-model-invocation: true,
# so the model will NOT auto-load it from natural language).
# Plugin-marketplace alternative (auto-updates, adds the always-on hook):
# claude plugin marketplace add ayghri/i-have-adhd
# claude plugin install i-have-adhd@i-have-adhd
# Always-on across sessions: touch ~/.claude/.i-have-adhd-always (SessionStart hook injects the ruleset)
# No external deps, no API key, no CLI. Pure prompt/output-shaping skill.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger I Have Adhd
-
/i-have-adhdReshapes replies for ADHD readers: action first, numbered steps, no preamble or closers
It also activates on plain-language prompts like these:
-
Explain this bug fix in clear numbered steps -
Break this plan into concrete next actions -
Keep track of state across our conversation
Frequently asked questions
- Is the I Have Adhd skill free?
- Yes. The skill itself is free from ayghri/i-have-adhd. SkillProof publishes the install command and an independent test verdict at no cost.
- Does I Have Adhd work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Located SKILL.md at skills/i-have-adhd/SKILL.md (also mirrored at .cursor/skills/); frontmatter parses with name+description and all spot-checked files return HTTP 200 (SKILL.md, hooks/always-on.sh, agents/openai.yaml). Read hooks/always-on.sh: clean POSIX sh, opt-in via a flag file, strips frontmatter and injects the body, exits 0 on failure — no curl|sh, base64, exfiltration, or hardcoded paths. For the output test I answered one coding question ("add a rate limiter to Express") twice: a baseline in my default voice (opened "Great question!", buried steps in prose, closed "Hope this helps") and a skill-following version (first line = runnable command, 3 numbered steps, "About 5 minutes" estimate, testable next action, Redis caveat deferred as a separate offer). The two artifacts differ concretely on 6 axes matching Rules 1,2,4,6,7,10. Note: disable-model-invocation:true means it only fires via /i-have-adhd or the always-on hook, which the description discloses honestly.
- What is the I Have Adhd SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install I Have Adhd?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use I Have Adhd with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.